A kernel-based approach to molecular conformation analysis

Abstract

We present a novel machine learning approach to understanding conformation dynamics of biomolecules. The approach combines kernel-based techniques that are popular in the machine learning community with transfer operator theory for analyzing dynamical systems in order to identify conformation dynamics based on molecular dynamics simulation data. We show that many of the prominent methods like Markov State Models, EDMD, and TICA can be regarded as special cases of this approach and that new efficient algorithms can be constructed based on this derivation. The results of these new powerful methods will be illustrated with several examples, in particular the alanine dipeptide and the protein NTL9.

References in corpus (10)

• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• VAMPnets: Deep learning of molecular kinetics
• Kernel Mean Embedding of Distributions: A Review and Beyond
• Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
• On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operator
• Data-driven model reduction and transfer operator approximation
• On the numerical approximation of the Perron-Frobenius and Koopman operator
• Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces
• Data-driven Computation of Molecular Reaction Coordinates
• Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces

Cited by in corpus (11)

• Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces
• Special Topic: Markov Models of Molecular Kinetics
• Kernel-based approximation of the Koopman generator and Schrödinger operator
• Kernel methods for detecting coherent structures in dynamical data
• Efficient Approximation of Molecular Kinetics using Random Fourier Features
• Koopman-based spectral clustering of directed and time-evolving graphs
• SafEDMD: A Koopman-based data-driven controller design framework for nonlinear dynamical systems
• Koopman Operator Dynamical Models: Learning, Analysis and Control
• Dynamical systems and complex networks: A Koopman operator perspective
• Learning Transfer Operators by Kernel Density Estimation
• A General Framework for Linking Free and Forced Fluctuations via Koopmanism